Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4599 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9575. Min Range: -6.9575
Max Act: 6.9575. Min Act: -0.1700
Data Index: 1538414 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9575. Min Range: -6.9575
Max Act: 6.6137. Min Act: -0.1700
Data Index: 1566770 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9575. Min Range: -6.9575
Max Act: 6.5200. Min Act: -0.1700
Data Index: 7513685 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9575. Min Range: -6.9575
Max Act: 6.4262. Min Act: -0.1700
Data Index: 8536358 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9575. Min Range: -6.9575
Max Act: 6.3950. Min Act: -0.1700
Data Index: 4492573 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9575. Min Range: -6.9575
Max Act: 6.3637. Min Act: -0.1700
Data Index: 5365601 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9575. Min Range: -6.9575
Max Act: 6.3325. Min Act: -0.1700
Data Index: 3975193 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9575. Min Range: -6.9575
Max Act: 6.3012. Min Act: -0.1700
Data Index: 3110028 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9575. Min Range: -6.9575
Max Act: 6.3325. Min Act: -0.1700
Data Index: 2411705 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9575. Min Range: -6.9575
Max Act: 6.3325. Min Act: -0.1700
Data Index: 2261426 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9575. Min Range: -6.9575
Max Act: 6.3637. Min Act: -0.1700
Data Index: 7364086 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9575. Min Range: -6.9575
Max Act: 6.3012. Min Act: -0.1700
Data Index: 894164 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9575. Min Range: -6.9575
Max Act: 6.3012. Min Act: -0.1700
Data Index: 1830323 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9575. Min Range: -6.9575
Max Act: 6.2700. Min Act: -0.1700
Data Index: 704465 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9575. Min Range: -6.9575
Max Act: 6.3012. Min Act: -0.1700
Data Index: 8749393 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9575. Min Range: -6.9575
Max Act: 6.2700. Min Act: -0.1700
Data Index: 6489076 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9575. Min Range: -6.9575
Max Act: 6.2700. Min Act: -0.1700
Data Index: 5165050 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9575. Min Range: -6.9575
Max Act: 6.2700. Min Act: -0.1700
Data Index: 1209823 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9575. Min Range: -6.9575
Max Act: 6.2387. Min Act: -0.1700
Data Index: 1814111 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9575. Min Range: -6.9575
Max Act: 6.2700. Min Act: -0.1700
Data Index: 1083407 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #19